Page 27 - A Practical Guide from Design Planning to Manufacturing

The Evolution of the Microprocessor 3

If I never changed the software on my computer, it is likely that at
some point it would become fast enough. Spell checking an entire large
document in a few seconds is a useful feature, but the capability to do
it a 100 times in a few seconds is overkill. What drives the need for per-
formance is new functionality. People will sometimes say they need to
buy a new computer because their old one has become too slow. This is
of course only a matter of perception. Their computer has the exact
same speed as the day they bought it. What has changed to make it
appear slower is the software. As the performance of computers
improves, new software is written to perform new tasks that require
higher performance, so that installing the latest software on a com-
puter that is a few years old makes it appear very slow indeed.
Being designed to run programs allows microprocessors to perform
many different functions, and rapid improvements in performance are
constantly allowing for new functions to be found. Continuing demand
for new applications funds manufacturing improvements, which make
possible these performance gains.
Despite all the different functions a microprocessor performs, in the
end it is only a collection of transistors and wires. The job of micro-
processor design is ultimately deciding how to connect transistors to be
able to quickly execute the commands that run programs. As the number
of transistors on a processor has grown from thousands to millions that
job has become steadily more complicated, but a microprocessor is still
just a collection of transistors connected to operate as the brain of a com-
puter. The story of the first microprocessor is therefore also the story of
the invention of the transistor and the integrated circuit.

The Transistor
In 1940, many experiments were performed with semiconductor crystals
to try and create better diodes. Diodes allow electricity to flow in one
direction but not the other and are required for radio and radar receivers.
Vacuum tube diodes could be used but did not work well at the high fre-
quencies required by accurate radar. Instead, crystals of semiconductors
were used. How these crystals worked was very poorly understood at the
time, but it was known that a metal needle touching the surface of some
crystals could form a diode. These cat whisker diodes could operate at
high frequencies but were extremely temperamental. The crystals had
many defects and impurities and so the user was required to try differ-
ent points on the crystal at random until finding one that worked well.
Any vibration could throw the whole apparatus off. This was an appli-
cation in need of a sturdy and reliable electrical switch.
®
At AT&T Bell Laboratories, Russell Ohl was working with a silicon
crystal when he noticed a very curious phenomenon. The crystal produced